ollama

Commit Graph

Author	SHA1	Message	Date
Jeffrey Morgan	856b8ec131	remove need for `$VSINSTALLDIR` since build will fail if `ninja` cannot be found (#3350 )	2 years ago
Daniel Hiltgen	d4c10df2b0	Add Radeon gfx940-942 GPU support	2 years ago
Daniel Hiltgen	540f4af45f	Wire up more complete CI for releases Flesh out our github actions CI so we can build official releaes.	2 years ago
Daniel Hiltgen	85129d3a32	Adapt our build for imported server.cpp	2 years ago
Daniel Hiltgen	6c5ccb11f9	Revamp ROCm support This refines where we extract the LLM libraries to by adding a new OLLAMA_HOME env var, that defaults to `~/.ollama` The logic was already idempotenent, so this should speed up startups after the first time a new release is deployed. It also cleans up after itself. We now build only a single ROCm version (latest major) on both windows and linux. Given the large size of ROCms tensor files, we split the dependency out. It's bundled into the installer on windows, and a separate download on windows. The linux install script is now smart and detects the presence of AMD GPUs and looks to see if rocm v6 is already present, and if not, then downloads our dependency tar file. For Linux discovery, we now use sysfs and check each GPU against what ROCm supports so we can degrade to CPU gracefully instead of having llama.cpp+rocm assert/crash on us. For Windows, we now use go's windows dynamic library loading logic to access the amdhip64.dll APIs to query the GPU information.	2 years ago
Jeffrey Morgan	efe040f8c0	reset with `init_vars` ahead of each cpu build in `gen_windows.ps1` (#2654 )	2 years ago
Daniel Hiltgen	df6dc4fd96	Fix duplicate menus on update and exit on signals Also fixes a few fit-and-finish items for better developer experience	2 years ago
Daniel Hiltgen	db2a9ad1fe	Explicitly disable AVX2 on GPU builds Even though we weren't setting it to on, somewhere in the cmake config it was getting toggled on. By explicitly setting it to off, we get `/arch:AVX` as intended.	2 years ago
Daniel Hiltgen	29e90cc13b	Implement new Go based Desktop app This focuses on Windows first, but coudl be used for Mac and possibly linux in the future.	2 years ago
Jeffrey Morgan	a64570dcae	Fix clearing kv cache between requests with the same prompt (#2186 ) * Fix clearing kv cache between requests with the same prompt * fix powershell script	2 years ago
Daniel Hiltgen	a447a083f2	Add compute capability 5.0, 7.5, and 8.0	2 years ago
Jeffrey Morgan	4c54f0ddeb	sign dylibs on macOS (#2101 )	2 years ago
Jeffrey Morgan	dc88cc3981	use `gzip` for runner embedding (#2067 )	2 years ago
Daniel Hiltgen	1b249748ab	Add multiple CPU variants for Intel Mac This also refines the build process for the ext_server build.	2 years ago
Daniel Hiltgen	39928a42e8	Always dynamically load the llm server library This switches darwin to dynamic loading, and refactors the code now that no static linking of the library is used on any platform	2 years ago
Bruce MacDonald	3367b5f3df	remove unused generate patches (#1810 )	2 years ago
Daniel Hiltgen	77d96da94b	Code shuffle to clean up the llm dir	2 years ago
Daniel Hiltgen	e9ce91e9a6	Load dynamic cpu lib on windows On linux, we link the CPU library in to the Go app and fall back to it when no GPU match is found. On windows we do not link in the CPU library so that we can better control our dependencies for the CLI. This fixes the logic so we correctly fallback to the dynamic CPU library on windows.	2 years ago
Jeffrey Morgan	29340c2e62	update cmake flags for `amd64` macOS (#1780 ) * update cmake flags for intel macOS * remove `LLAMA_K_QUANTS` * put back `CMAKE_OSX_DEPLOYMENT_TARGET` and disable `LLAMA_F16C`	2 years ago
Daniel Hiltgen	738a8d12eb	Rename the ollama cmakefile	2 years ago
Daniel Hiltgen	d966b730ac	Switch windows build to fully dynamic Refactor where we store build outputs, and support a fully dynamic loading model on windows so the base executable has no special dependencies thus doesn't require a special PATH.	2 years ago
Daniel Hiltgen	9a70aecccb	Refactor how we augment llama.cpp This changes the model for llama.cpp inclusion so we're not applying a patch, but instead have the C++ code directly in the ollama tree, which should make it easier to refine and update over time.	2 years ago
Daniel Hiltgen	e5202eb687	Quiet down llama.cpp logging by default By default builds will now produce non-debug and non-verbose binaries. To enable verbose logs in llama.cpp and debug symbols in the native code, set `CGO_CFLAGS=-g`	2 years ago
Daniel Hiltgen	d9cd3d9667	Revive windows build The windows native setup still needs some more work, but this gets it building again and if you set the PATH properly, you can run the resulting exe on a cuda system.	2 years ago
Daniel Hiltgen	35934b2e05	Adapted rocm support to cgo based llama.cpp	2 years ago
Daniel Hiltgen	d4cd695759	Add cgo implementation for llama.cpp Run the server.cpp directly inside the Go runtime via cgo while retaining the LLM Go abstractions.	2 years ago

21 Commits (856b8ec1318c49d0b76650374014dfba4b9f4257)